Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    invention relates to the present disclosure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peut
    0.46
     cực
    0.46
     keySchedule
    0.44
     olabilir
    0.44
     Como
    0.43
     può
    0.42
     inglês
    0.42
     pode
    0.42
     pueden
    0.42
     डेफ
    0.41
    POSITIVE LOGITS
     ASEAN
    0.44
    andingan
    0.42
     BO
    0.40
     subsidized
    0.39
    atelle
    0.39
     necessities
    0.38
     advertising
    0.37
    시아
    0.37
     smuggled
    0.37
     receptacles
    0.37
    Act Density 0.001%

    No Known Activations